English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Due to increasing concerns about environmental impact, operating costs, andenergy security, public transit agencies are seeking to reduce their fuel useby employing electric vehicles (EVs). However, because of the high upfront costof EVs, most agencies can afford only mixed fleets of internal-combustion andelectric vehicles. Making the best use of these mixed fleets presents achallenge for agencies since optimizing the assignment of vehicles to transitroutes, scheduling charging, etc. require accurate predictions of electricityand fuel use. Recent advances in sensor-based technologies, data analytics, andmachine learning enable remedying this situation; however, to the best of ourknowledge, there exists no framework that would integrate all relevant datainto a route-level prediction model for public transit. In this paper, wepresent a novel framework for the data-driven prediction of route-level energyuse for mixed-vehicle transit fleets, which we evaluate using data collectedfrom the bus fleet of CARTA, the public transit authority of Chattanooga, TN.We present a data collection and storage framework, which we use to capturesystem-level data, including traffic and weather conditions, and high-frequencyvehicle-level data, including location traces, fuel or electricity use, etc. Wepresent domain-specific methods and algorithms for integrating and cleansingdata from various sources, including street and elevation maps. Finally, wetrain and evaluate machine learning models, including deep neural networks,decision trees, and linear regression, on our integrated dataset. Our resultsshow that neural networks provide accurate estimates, while other models canhelp us discover relations between energy use and factors such as road andweather conditions.

Data-Driven Prediction of Route-Level Energy Use for Mixed-Vehicle Transit Fleets